ClawHub
Back to skill

Security audit

Game Theory Debate

Security checks for vulnerabilities and agentic risk

Overview

This is a prompt-only decision-analysis skill with broad activation language and optional memory references, but no hidden code, network access, installation steps, or destructive behavior.

Install this if you want decision requests to be answered with a structured game-theory debate format. Be aware it may trigger on ordinary indecision or comparison questions, and do not allow long-term memory updates unless you want past decision outcomes reused later.

A.I.G

Vulnerability Patterns
  • Skill Instruction HijackingAlters the agent's session goals or safety constraints when the skill loads
  • Agent Memory PoisoningWrites attacker-controlled rules into memory that affect later sessions
  • Remote Payload Retrieval and ExecutionFetches external code whose behavior can change after review
  • Embedded Malicious CodeShips malicious scripts inside the skill and executes them locally
  • Unauthorized Access and Privilege EscalationObtains permissions beyond the task's legitimate needs

SkillSpector

Vulnerability Patterns
  • Trigger AbuseOverly Broad Trigger, Shadow Command Trigger, Keyword Baiting Trigger
  • Prompt InjectionInstruction Override, Hidden Instructions, Exfiltration Commands
  • Data ExfiltrationExternal Transmission, Env Variable Harvesting, File System Enumeration
  • Privilege EscalationExcessive Permissions, Sudo/Root Execution, Credential Access
  • Supply ChainUnpinned Dependencies, External Script Fetching, Obfuscated Code
Findings (2)

Vague Triggers

Medium
Confidence
96% confidence
Finding
The auto-trigger phrases are very broad, including common conversational patterns like asking for advice or expressing indecision. This can cause the skill to activate unexpectedly in ordinary chats, leading to unwanted steering of the conversation, unnecessary hidden workflow changes, and possible interference with user intent or other skills.

Natural-Language Policy Violations

Low
Confidence
91% confidence
Finding
Natural-language content throughout the file is presented exclusively in Chinese, and the skill does not state that the user may choose another language. This can amount to a language-policy violation when the skill implicitly forces one locale without user opt-in or documented justification.

Static analysis

No suspicious patterns detected.